Learning wind fields with multiple kernels

This paper presents multiple kernel learning (MKL) regression as an exploratory spatial data analysis and modelling tool. The MKL approach is introduced as an extension of support vector regression, where MKL uses dedicated kernels to divide a given task into sub-problems and to treat them separately in an effective way. It provides better interpretability to non-linear robust kernel regression at the cost of a more complex numerical optimization. In particular, we investigate the use of MKL as a tool that allows us to avoid using ad-hoc topographic indices as covariables in statistical models in complex terrains. Instead, MKL learns these relationships from the data in a non-parametric fashion. A study on data simulated from real terrain features confirms the ability of MKL to enhance the interpretability of data-driven models and to aid feature selection without degrading predictive performances. Here we examine the stability of the MKL algorithm with respect to the number of training data samples and to the presence of noise. The results of a real case study are also presented, where MKL is able to exploit a large set of terrain features computed at multiple spatial scales, when predicting mean wind speed in an Alpine region.

Multiple Kernel Learning of Environmental Data. Case study: Analysis and Mapping of Wind Fields

The paper presents the Multiple Kernel Learning (MKL) approach as a modelling and data exploratory tool and applies it to the problem of wind speed mapping. Support Vector Regression (SVR) is used to predict spatial variations of the mean wind speed from terrain features (slopes, terrain curvature, directional derivatives) generated at different spatial scales. Multiple Kernel Learning is applied to learn kernels for individual features and thematic feature subsets, both in the context of feature selection and optimal parameters determination. An empirical study on real-life data confirms the usefulness of MKL as a tool that enhances the interpretability of data-driven models.

Dépistage et intervention brève par internet pour la consommation d'alcool a risque: www.alcooquizz.ch [Web-based screening and brief intervention for unhealthy alcohol use: www.alcooquizz.ch].

Many individuals with unhealthy alcohol use have few or no contact with the health care system and are therefore unlikely to receive information or a brief intervention from a health care professional. Consequently, many Internet-based interventions have been developed. These interventions can reach a large population. We present in this report www.alcooquizz.ch, a website providing tailored feedback and information on alcohol use and its consequences. In six months and a half, more than 15000 individuals visited the website. It appropriately targets individuals with unhealthy alcohol use and users' satisfaction was high. Internet is a valuable option to provide health related information and secondary prevention interventions for unhealthy alcohol use.

Catalogue des 17 tableaux originaux... composant la collection de feu M. le marquis de Saint-Marc... / [expert] Ch. Rouillard

[Vente. Art. 1859-02-23. Paris]

Catalogue de tableaux anciens et modernes de diverses écoles provenant de la succession de M. André Leroux... / [expert] Ch. Rouillard

[Vente. Art. 1859-05-14. Paris]